← Monday, September 28, 2026InferencePaper

PISA uses hierarchical Top-K selection for O(N log N) sparse attention

huggingface.co by Bohao Tang et al. Editor score 7/10

PISA narrows attention candidates through a coarse-to-fine hierarchy, with Triton kernels that fuse routing and scoring without materializing the query-key matrix. Its stated O(N log N) complexity targets a major bottleneck in long-context attention.

What: PISA is a block-sparse attention method that selects retained key blocks with a hierarchical Top-K strategy.
Method: It narrows candidates from coarse to fine using LogSumExp scoring over bounded sets, with O(N log N) complexity and fused Triton kernels.
Why it matters: Reducing block-selection cost can make long-context attention more efficient without materializing the query-key score matrix.

PISA repeatedly scores bounded candidates while narrowing selection from coarse to fine levels. Sketched from the article's own text.

Read on huggingface.co →

Discussion

Discussion is not switched on yet. Use Note above to keep your own thoughts on this story.

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.